Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A system for regulating fluid flow having a processor configured to reduce image noise, the system comprising: an image sensor configured to capture an image of a drip chamber; and a valve configured to regulate fluid flowing from the drip chamber to a patient, wherein the processor is configured to: capture the image of the drip chamber using the image sensor, perform an edge detection on the image to generate a first processed image, and perform an AND-operation on a pixel on a first side of an axis of the first processed image with a corresponding mirror pixel on a second side of the axis of the first processed image to generate a second processed image.
This invention relates to a system for regulating fluid flow in medical applications, specifically addressing the challenge of accurately monitoring and controlling intravenous (IV) fluid administration. The system includes an image sensor that captures images of a drip chamber, where fluid droplets form during infusion. A processor analyzes these images to detect and track fluid flow, ensuring precise delivery to a patient. The processor reduces image noise by performing edge detection on the captured image to generate a first processed image, which highlights the boundaries of droplets. To further refine the image, the processor performs a logical AND-operation between pixels on one side of a central axis and their mirrored counterparts on the opposite side, producing a second processed image that enhances symmetry and reduces noise. This processed data is used to regulate a valve that controls the fluid flow from the drip chamber to the patient, ensuring accurate and safe administration. The system improves reliability in fluid monitoring by minimizing noise interference, which is critical in medical settings where precise flow control is essential.
2. The system according to claim 1 , wherein the edge detection is performed using a canny edge detection.
A system for image processing that includes edge detection to identify boundaries within an image. The system enhances image analysis by applying a Canny edge detection algorithm, which is a multi-stage process involving noise reduction, gradient calculation, non-maximum suppression, and hysteresis thresholding. This method improves edge detection accuracy by reducing false positives and preserving true edges. The system may also include preprocessing steps such as image filtering or normalization to optimize edge detection performance. The Canny algorithm is particularly effective in identifying sharp transitions in pixel intensity, making it useful in applications like object recognition, medical imaging, and autonomous navigation. The system may further integrate the detected edges into higher-level image analysis tasks, such as segmentation or feature extraction, to support decision-making processes in automated systems. By leveraging the Canny edge detection method, the system achieves robust and reliable edge identification, enhancing the overall accuracy of image-based applications.
3. The system according to claim 1 , wherein the processor is configured to match a template to the image.
The system is designed for image processing, specifically for matching a template to an image. The system includes a processor that analyzes an input image and compares it to a predefined template. The template matching process involves identifying and aligning features of the template within the image, allowing for accurate detection or recognition of objects, patterns, or structures. This technology is useful in applications such as object detection, quality control in manufacturing, medical imaging, and automated inspection systems. The system may also include additional components, such as an image capture device to acquire the input image and a memory to store the template and intermediate processing data. The processor performs the matching by applying algorithms that evaluate spatial relationships, pixel intensity, or other image characteristics to determine the best fit between the template and regions of the image. The system may further include a display or output interface to present the results of the template matching process, such as highlighting detected objects or providing coordinates of matched regions. The technology addresses challenges in automated image analysis, where precise and reliable detection of predefined patterns is required.
4. The system of claim 3 , wherein the template includes at least a partial image of a drop of the fluid forming within the drip chamber.
This invention relates to fluid monitoring systems, specifically for tracking fluid levels and drop formation in medical or laboratory drip chambers. The system addresses the challenge of accurately detecting and analyzing fluid drops within a transparent or translucent chamber to ensure proper fluid administration or measurement. The system includes a template that incorporates at least a partial image of a fluid drop forming within the drip chamber. This template is used to compare against real-time images captured by a sensor, such as a camera, to identify and analyze drop formation. The template may include reference features like drop shape, size, or position to enhance detection accuracy. The system may also include a light source to improve image clarity and a processor to analyze the captured images against the template. By using the template, the system can reliably monitor fluid flow, detect anomalies, and ensure precise fluid delivery or measurement in applications like intravenous therapy or laboratory experiments. The invention improves upon existing systems by providing a more accurate and consistent method for drop detection, reducing errors in fluid administration or measurement.
5. The system of claim 1 , wherein the processor is configured to apply a blurring function to the image captured by the image sensor of the drip chamber.
This invention relates to a medical monitoring system for intravenous (IV) fluid administration, specifically focusing on improving the accuracy of drip rate detection in a drip chamber. The system addresses the challenge of accurately measuring fluid flow rates in IV lines, where factors such as lighting conditions, motion, or optical interference can distort the captured images, leading to inaccurate drip rate calculations. The system includes an image sensor positioned to capture images of the drip chamber, where fluid droplets form and fall. A processor analyzes these images to determine the drip rate. To enhance accuracy, the processor applies a blurring function to the captured images before processing. This blurring function reduces noise and sharpens the distinction between droplets and the background, improving the system's ability to detect and count individual drips reliably. The blurring function may involve Gaussian blurring, median filtering, or other image processing techniques to smooth the image while preserving the relevant features of the droplets. The system may also include additional components, such as a light source to illuminate the drip chamber uniformly, ensuring consistent image quality. The processor may further apply edge detection or pattern recognition algorithms to identify droplet shapes and track their movement, enabling precise drip rate calculations. By improving image clarity and reducing noise, the system ensures accurate monitoring of IV fluid administration, which is critical for patient safety and treatment efficacy.
6. The system according to claim 5 , wherein the blurring function is a low pass filter.
A system for image processing includes a blurring function applied to an input image to reduce noise or enhance certain features. The blurring function is implemented as a low pass filter, which attenuates high-frequency components while preserving low-frequency components. This filtering process smooths the image by reducing sharp transitions and noise, improving visual quality or preparing the image for further analysis. The system may include additional components, such as an image acquisition module to capture the input image and a processing unit to apply the low pass filter. The filtered output can be used for tasks like object detection, edge enhancement, or noise reduction in various applications, including medical imaging, surveillance, and automotive systems. The low pass filter may be implemented using digital signal processing techniques, such as convolution with a Gaussian kernel or a moving average filter, to achieve the desired smoothing effect. The system ensures that the filtered image retains essential structural information while minimizing unwanted artifacts.
7. The system according to claim 5 , wherein the blurring function is configured to blur in a vertical direction.
A system for image processing includes a blurring function that applies a blur effect to an image in a vertical direction. The system is designed to reduce noise or enhance specific features in digital images by selectively blurring vertical elements while preserving horizontal details. This approach is particularly useful in applications where vertical artifacts or noise need to be minimized without distorting horizontal structures, such as in medical imaging, satellite imagery, or video processing. The blurring function operates by applying a filter that smooths pixel values along vertical lines, effectively reducing high-frequency variations in the vertical direction. The system may also include additional components, such as an input module for receiving image data and an output module for displaying or storing the processed image. The vertical blurring function can be adjusted based on user preferences or automated settings to achieve the desired level of smoothing. This technique improves image clarity and reduces visual artifacts while maintaining the integrity of horizontal features.
8. The system according to claim 5 , wherein the blurring function is configured to blur in a horizontal direction.
A system for image processing is designed to enhance visual privacy by selectively blurring regions of an image. The system includes a processing unit that applies a blurring function to specific areas of an image, such as faces or sensitive information, to obscure details while preserving the rest of the image. The blurring function is specifically configured to apply blurring in a horizontal direction, which can be useful for certain privacy applications where vertical details remain intact. The system may also include an input interface for receiving the image and an output interface for displaying or transmitting the processed image. The processing unit may further include a detection module to identify regions requiring blurring, ensuring targeted and efficient privacy protection. This approach allows for controlled obscuration of sensitive content while maintaining the overall visual context of the image. The horizontal blurring technique can be particularly effective in scenarios where vertical information, such as text or vertical features, needs to be preserved. The system may be integrated into surveillance cameras, digital imaging devices, or software applications to automate privacy protection in real-time or post-processing workflows.
9. The system according to claim 5 , wherein the blurring function is a one-dimensional Gaussian Blur function.
A system for image processing applies a one-dimensional Gaussian Blur function to enhance image quality. The system processes images by selectively blurring specific regions to reduce noise or artifacts while preserving important features. The Gaussian Blur function smooths the image along a single axis, either horizontally or vertically, to minimize distortions caused by high-frequency noise or compression artifacts. This technique is particularly useful in applications where maintaining sharpness in one direction is critical, such as in medical imaging, satellite imagery, or video compression. The system may include preprocessing steps to identify regions requiring blurring and post-processing to ensure the final output meets quality standards. The one-dimensional approach reduces computational complexity compared to two-dimensional blurring while effectively addressing targeted noise reduction. This method improves image clarity and reduces visual artifacts without excessive smoothing, making it suitable for real-time applications where processing efficiency is important.
10. The system according to claim 5 , wherein the blurring function is a two-dimensional Gaussian Blur function.
A system for image processing applies a two-dimensional Gaussian Blur function to reduce noise or enhance visual effects in digital images. The system processes an input image by applying a Gaussian Blur, which smooths the image by averaging pixel values within a defined neighborhood, weighted by a Gaussian distribution. This function is particularly useful for reducing high-frequency noise, softening edges, or preparing images for further processing. The Gaussian Blur is characterized by its standard deviation, which controls the extent of blurring, and kernel size, which determines the area of influence. The system may integrate this blurring function into a larger image processing pipeline, where it can be applied before or after other operations such as edge detection, segmentation, or feature extraction. The two-dimensional Gaussian Blur ensures isotropic smoothing, meaning the blurring effect is uniform in all directions. This approach is widely used in computer vision, medical imaging, and photography to improve image quality or prepare data for machine learning models. The system may also include adjustable parameters to allow users to fine-tune the blurring effect based on specific application requirements.
11. A method for reducing image noise, the method comprising: capturing an image of a drip chamber; performing an edge detection on the image to generate a first processed image, and performing an AND-operation on a pixel on a first side of an axis of the first processed image with a corresponding mirror pixel on a second side of the axis of the first processed image to generate a second processed image.
This invention relates to image processing techniques for reducing noise in images of drip chambers, which are commonly used in medical devices to monitor fluid levels. The problem addressed is the presence of noise in captured images, which can obscure important features such as fluid levels or drip rates, leading to inaccurate monitoring. The method involves capturing an image of the drip chamber and then applying edge detection to enhance the relevant features while suppressing noise. The edge detection generates a first processed image where edges are highlighted. To further reduce noise, the method performs a symmetry-based operation: for each pixel on one side of a central axis, it compares it with its mirrored counterpart on the opposite side. An AND-operation is applied between these mirrored pixels to generate a second processed image. This operation retains only the pixels that are consistent across both sides, effectively filtering out noise while preserving the symmetrical features of the drip chamber. The result is a cleaner image with reduced noise, improving the accuracy of fluid level monitoring in medical applications.
12. The method according to claim 11 , wherein the act of performing the edge detection includes performing a canny edge detection.
A method for image processing involves detecting edges within an image to identify boundaries or significant transitions in pixel intensity. The method employs a canny edge detection algorithm, which is a multi-stage process designed to accurately and efficiently detect edges in digital images. The canny edge detection algorithm includes noise reduction through Gaussian blurring, gradient calculation to identify intensity changes, non-maximum suppression to thin edges, and hysteresis thresholding to determine strong and weak edges. This approach enhances edge detection accuracy while minimizing false positives and noise interference. The method is particularly useful in applications requiring precise edge identification, such as computer vision, medical imaging, and autonomous navigation, where accurate edge detection is critical for further image analysis or object recognition. The use of canny edge detection ensures robust performance in varying lighting conditions and complex backgrounds, improving the reliability of subsequent processing steps.
13. The method according to claim 11 , further comprising matching a template to the image.
The invention relates to image processing, specifically to methods for analyzing and interpreting images, particularly in applications such as object recognition, pattern matching, or automated inspection. The core problem addressed is the need for accurate and efficient template matching in image analysis, where a predefined template is compared to an image to identify specific features or objects. The method involves capturing an image and then applying a template matching technique to align or identify the template within the image. The template matching process compares the template to regions of the image to find the best match, which may involve techniques such as correlation, feature extraction, or machine learning-based pattern recognition. The method may also include preprocessing steps, such as noise reduction or contrast enhancement, to improve matching accuracy. Additionally, the method may adjust the template or image parameters, such as scaling, rotation, or translation, to optimize the matching process. The result is a precise identification or alignment of the template within the image, enabling applications like quality control, medical imaging, or autonomous navigation. The invention improves upon prior methods by enhancing the robustness and efficiency of template matching in real-world scenarios.
14. The method according to claim 13 , wherein the template includes at least a partial image of a drop of the fluid forming within the drip chamber.
This invention relates to fluid monitoring systems, specifically for detecting and analyzing fluid drops within a drip chamber, such as those used in medical infusion devices. The problem addressed is the need for accurate and reliable detection of fluid drops to ensure proper fluid delivery rates and prevent errors in medical treatments. The method involves using a template that includes at least a partial image of a fluid drop forming within the drip chamber. This template is compared against captured images of the drip chamber to identify and analyze the fluid drops. The template may include a portion of the drop's shape, size, or other distinguishing features to enhance detection accuracy. By matching the template to the captured images, the system can determine the presence, size, and timing of fluid drops, allowing for precise monitoring of fluid flow rates. The method improves upon existing systems by providing a more robust and flexible detection mechanism, reducing false positives and ensuring reliable operation even under varying lighting or environmental conditions. This is particularly important in medical applications where accurate fluid delivery is critical for patient safety. The use of a partial drop image in the template allows for more efficient processing and better adaptation to different types of fluid drops and drip chamber designs.
15. The method according to claim 11 , further comprising applying a blurring function to the image of the drip chamber.
A system and method for monitoring intravenous (IV) fluid administration involves capturing images of an IV drip chamber to detect and analyze fluid droplets. The method includes illuminating the drip chamber with a light source, capturing images of the chamber using an imaging device, and processing the images to detect and measure the size, shape, and timing of fluid droplets. This data is used to determine the flow rate of the IV fluid, ensuring accurate and consistent administration. The method further includes applying a blurring function to the captured images of the drip chamber to reduce noise and enhance the clarity of the droplets, improving the accuracy of subsequent measurements. The system may also include a calibration process to account for variations in lighting, imaging device sensitivity, and chamber geometry. The method can be integrated into a monitoring device that provides real-time feedback to healthcare providers, alerting them to deviations from prescribed flow rates or potential blockages in the IV line. This technology addresses the need for precise and reliable IV fluid administration, reducing the risk of under- or over-infusion, which can lead to complications in patient care.
16. The method according to claim 15 , wherein the blurring function is a low pass filter.
A method for image processing involves applying a blurring function to an image to reduce noise or enhance certain features. The blurring function is specifically implemented as a low pass filter, which attenuates high-frequency components in the image while preserving lower-frequency details. This technique is useful in applications such as noise reduction, edge preservation, and pre-processing for further image analysis. The low pass filter may be applied uniformly across the entire image or selectively to specific regions based on predefined criteria. The method ensures that the filtered image retains essential structural information while minimizing unwanted artifacts. This approach is particularly beneficial in medical imaging, surveillance, and computer vision tasks where clarity and accuracy are critical. The low pass filter can be implemented using various algorithms, including Gaussian, box, or median filters, depending on the desired smoothing effect and computational efficiency. The method may also include additional steps such as adjusting filter parameters dynamically based on image content or user input to optimize performance.
17. The method according to claim 15 , wherein the act of applying the blurring function comprises blurring in a vertical direction.
A method for image processing involves applying a blurring function to an image to reduce noise or enhance certain features. The blurring function is specifically applied in a vertical direction, meaning the smoothing operation is performed along vertical lines of the image rather than horizontally or in a combined direction. This vertical blurring can be used to preserve horizontal details while reducing vertical noise, which is useful in applications like text recognition, where horizontal lines (such as text characters) should remain sharp while vertical artifacts are minimized. The method may involve selecting a kernel or filter that emphasizes vertical smoothing, such as a Gaussian blur applied only in the vertical axis. This approach can be part of a larger image preprocessing pipeline, where the vertical blurring step is combined with other operations like edge detection or contrast adjustment to improve image quality for further analysis or display. The technique is particularly beneficial in scenarios where vertical noise is more prevalent or where horizontal features need to be preserved for accurate interpretation.
18. The method according to claim 15 , wherein the act of applying the blurring function comprises blurring in a horizontal direction.
A method for image processing involves applying a blurring function to an image to reduce noise or enhance certain features. The blurring function is specifically applied in a horizontal direction, meaning it smooths variations along horizontal lines while preserving vertical details. This directional blurring is useful in applications where vertical structures or edges need to be maintained, such as in text recognition or medical imaging. The method may involve preprocessing the image to identify regions of interest before applying the horizontal blur, ensuring that only relevant areas are affected. The blurring function can be adjusted based on the image content, such as varying the blur intensity or kernel size to optimize noise reduction without excessive distortion. This technique is particularly beneficial in scenarios where vertical alignment or sharpness is critical, such as in document scanning or satellite imagery analysis. The horizontal blurring helps maintain readability or structural integrity while reducing unwanted artifacts.
19. The method according to claim 15 , wherein the blurring function is a one-dimensional Gaussian Blur function.
A method for image processing involves applying a blurring function to an image to reduce noise or enhance certain features. The blurring function is specifically a one-dimensional Gaussian Blur function, which smooths the image along a single axis, either horizontally or vertically. This selective blurring can preserve edges or details in the orthogonal direction while reducing noise or artifacts in the chosen direction. The method may be part of a larger image processing pipeline that includes preprocessing steps, such as noise reduction or edge detection, followed by the application of the Gaussian Blur. The one-dimensional Gaussian Blur function is defined by a kernel that applies a weighted average to pixel values, with weights determined by a Gaussian distribution. This approach is useful in applications like medical imaging, where preserving certain features while reducing noise in a specific direction is critical. The method can be implemented in software, hardware, or a combination of both, and may be applied to static images, video frames, or real-time image streams. The use of a one-dimensional Gaussian Blur allows for more controlled smoothing compared to a two-dimensional blur, making it suitable for tasks requiring directional sensitivity.
20. The method according to claim 15 , wherein the blurring function is a two-dimensional Gaussian Blur function.
A method for image processing involves applying a blurring function to an image to reduce noise or enhance certain features. The blurring function is specifically a two-dimensional Gaussian Blur, which smooths the image by convolving it with a Gaussian kernel. This kernel has a defined standard deviation that controls the extent of blurring, with larger values producing more pronounced smoothing effects. The Gaussian Blur is applied uniformly across the image, ensuring consistent noise reduction or feature enhancement. The method may also include preprocessing steps, such as image segmentation or edge detection, to isolate regions of interest before applying the blur. The Gaussian Blur is particularly effective in preserving edges while reducing high-frequency noise, making it useful in applications like medical imaging, satellite imagery, and computer vision tasks. The method can be implemented in software or hardware, with adjustable parameters to tailor the blurring effect to specific requirements. The two-dimensional Gaussian Blur ensures isotropic smoothing, meaning the blur is applied equally in all directions, which is critical for maintaining image integrity in various analytical and visualization applications.
Unknown
November 24, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.